Chandrakant Deelip Kokane

Dr. Chandrakant Deelip Kokane


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 July 2023
Verified
Book Chapter
Closed access
PDF file
CKChandrakant Deelip Kokane
Chandrakant Deelip Kokane
SBSachin D. Babar
Sachin D. Babar
PMParikshit N. Mahalle
Parikshit N. Mahalle
SPShivprasad P. Patil
Shivprasad P. Patil

19 March 2021
Verified
Book Chapter
Closed access
PDF file
CKChandrakant Deelip Kokane
Chandrakant Deelip Kokane
SBSachin D. Babar
Sachin D. Babar
PMParikshit N. Mahalle
Parikshit N. Mahalle

27 October 2023 in International Journal on Recent and Innovation Trends in Computing and Communication
Verified
Journal Article
Open access
PDF file
CKChandrakant Deelip Kokane
Chandrakant Deelip Kokane
KPKishor R Pathak
Kishor R Pathak
GMGopal Mohadikar
Gopal Mohadikar
RPRakhi Subhash Pagar
Rakhi Subhash Pagar
SCSuhas Chavan
Suhas Chavan
SKSopan Bapu Kshirsagar
Sopan Bapu Kshirsagar
In today's daily life we are getting so many anonymous calls. Some calls are related to loan marketing and finance. As per the survey, one person is getting 26% spam calls in a day. The proposed methodology accepts user calls and based on the conversation the spam numbers are identified and the same information is provided to the other callers. This is possible because of machine learning-based sentiment analysis. Sentiment analysis is the subdomain of machine learning. The goal of this research is to propose an adaptive methodology for incoming calls. The sentiment-based incoming calls help desk works with freely available lexical resources WordNet, SemCor, and OMSTI. The discussed methodology accepts user conversations in audio format the speech-to-text conversion of the audio will be done. After pre-processing the keyword is detected from the statement. The word2Vec word embedding technique is used for representing words from document space to vector space. The 150-200 dimensional word vector is generated. The WordNet is used for sense mapping and keyword identification. Based on the sentiment analysis of input calls the decision is taken whether to accept or reject calls. This methodology is generating superior results for supervised machine learning models.

22 November 2024
Verified
Book Chapter
Closed access
PDF file
SASamir N. Ajani
Samir N. Ajani
SSSamit Shivadekar
Samit Shivadekar
VPVaidehi Pareek
Vaidehi Pareek
IJIra Joshi
Ira Joshi
DNDattatraya Babanrao Nalawade
Dattatraya Babanrao Nalawade
CKChandrakant Deelip Kokane
Chandrakant Deelip Kokane

18 March 2023
Verified
Book Chapter
Closed access
PDF file
CKChandrakant Deelip Kokane
Chandrakant Deelip Kokane
SBSachin Babar
Sachin Babar
PMParikshit Mahalle
Parikshit Mahalle

1 January 2024
Verified
Journal Article
Open access
PDF file
CKChandrakant Deelip Kokane
Chandrakant Deelip Kokane
RPRakhi Subhash Pagar
Rakhi Subhash Pagar
KPKishor Pathak
Kishor Pathak
YSYogesh Shepal
Yogesh Shepal
DKDeepali Kolte-Patil
Deepali Kolte-Patil
SPSonali Patil
Sonali Patil
Diabetes mellitus is a widespread health problem that puts people's health at great risk and puts a lot of stress on healthcare systems around the world. Early detection and forecast of diabetes are very important for managing and preventing the disease. One potential way to improve diabetes risk forecast is to use the power of artificial intelligence (AI) in health information data. The study's goal is to test and apply AI systems that can figure out a person's chance of getting diabetes by looking at a lot of health information, such as demographic, clinical, and lifestyle data. Several AI methods are used in our method, such as logistic regression, decision trees, support vector machines (SVM), and deep learning models like artificial neural networks (ANN). These methods were chosen because they have been shown to work well with complicated, high-dimensional health data. A lot of information from electronic health records (EHRs) is used in the study. This information includes patient details, medical history, lab test results, and lifestyle factors. To make sure the data was correct and useful, it was put through steps like normalization, handling missing numbers, and feature selection. We used a method called stratified k-fold cross-validation to train and test the models. This made sure that the evaluations were accurate and reduced the chance of overfitting. Key performance indicators like F1 score, accuracy, precision, recall, and the area under the receiver operating characteristic curve (AUC-ROC) were used to judge the model's performance. When the algorithms were compared, it was found that deep learning models, especially the ANN, were better at predicting diabetes risk (with an AUC-ROC of 0.92). The feature importance analysis showed that body mass index (BMI), fasting blood glucose levels, age, and a history of diabetes in the family are all strong factors of diabetes risk. We also looked into how AI models can be understood by using methods like SHapley Additive Explanations (SHAP) to show how different traits affect the results of predictions. This ability to be interpreted is very important for getting clinical insights and building trust among healthcare professionals. Our results show that AI systems might be able to correctly guess who will get diabetes, which would allow for early prevention and more personalized treatment plans.